powermove72
commited on
Commit
•
b3e6e41
1
Parent(s):
4efcfe1
Upload folder using huggingface_hub
Browse files- README.md +57 -0
- config.json +26 -0
- mergekit_config.yml +12 -0
- model-00001-of-00023.safetensors +3 -0
- model-00002-of-00023.safetensors +3 -0
- model-00003-of-00023.safetensors +3 -0
- model-00004-of-00023.safetensors +3 -0
- model-00005-of-00023.safetensors +3 -0
- model-00006-of-00023.safetensors +3 -0
- model-00007-of-00023.safetensors +3 -0
- model-00008-of-00023.safetensors +3 -0
- model-00009-of-00023.safetensors +3 -0
- model-00010-of-00023.safetensors +3 -0
- model-00011-of-00023.safetensors +3 -0
- model-00012-of-00023.safetensors +3 -0
- model-00013-of-00023.safetensors +3 -0
- model-00014-of-00023.safetensors +3 -0
- model-00015-of-00023.safetensors +3 -0
- model-00016-of-00023.safetensors +3 -0
- model-00017-of-00023.safetensors +3 -0
- model-00018-of-00023.safetensors +3 -0
- model-00019-of-00023.safetensors +3 -0
- model-00020-of-00023.safetensors +3 -0
- model-00021-of-00023.safetensors +3 -0
- model-00022-of-00023.safetensors +3 -0
- model-00023-of-00023.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +48 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- janai-hq/trinity-v1
|
7 |
+
- argilla/notus-7b-v1
|
8 |
+
base_model:
|
9 |
+
- janai-hq/trinity-v1
|
10 |
+
- argilla/notus-7b-v1
|
11 |
+
---
|
12 |
+
|
13 |
+
# Trinity_Notus2-xb
|
14 |
+
|
15 |
+
Trinity_Notus2-xb is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1)
|
17 |
+
* [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: janai-hq/trinity-v1
|
25 |
+
layer_range: [0, 26]
|
26 |
+
- sources:
|
27 |
+
- model: argilla/notus-7b-v1
|
28 |
+
layer_range: [8, 32]
|
29 |
+
merge_method: passthrough
|
30 |
+
tokenizer_source: union
|
31 |
+
dtype: float16
|
32 |
+
```
|
33 |
+
|
34 |
+
## 💻 Usage
|
35 |
+
|
36 |
+
```python
|
37 |
+
!pip install -qU transformers accelerate
|
38 |
+
|
39 |
+
from transformers import AutoTokenizer
|
40 |
+
import transformers
|
41 |
+
import torch
|
42 |
+
|
43 |
+
model = "powermove72/Trinity_Notus2-xb"
|
44 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
45 |
+
|
46 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
47 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
48 |
+
pipeline = transformers.pipeline(
|
49 |
+
"text-generation",
|
50 |
+
model=model,
|
51 |
+
torch_dtype=torch.float16,
|
52 |
+
device_map="auto",
|
53 |
+
)
|
54 |
+
|
55 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
56 |
+
print(outputs[0]["generated_text"])
|
57 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "janai-hq/trinity-v1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 50,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: janai-hq/trinity-v1
|
5 |
+
layer_range: [0, 26]
|
6 |
+
- sources:
|
7 |
+
- model: argilla/notus-7b-v1
|
8 |
+
layer_range: [8, 32]
|
9 |
+
merge_method: passthrough
|
10 |
+
tokenizer_source: union
|
11 |
+
dtype: float16
|
12 |
+
|
model-00001-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700b0d8a60bc333cff76cca3f2950d36c844dc755141c6e10799f636b37ebf5f
|
3 |
+
size 960521544
|
model-00002-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a17f8b1f6e24efde2daf1931d706c1b134e98ec533587af0b1af7e409b136e1
|
3 |
+
size 905995856
|
model-00003-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb07aa76c1accc920b4ecbde371e504aa4037b489ee7e067f9e5886d7f52cf6d
|
3 |
+
size 989890704
|
model-00004-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49de7872b254a003e347441c95362ccbfaafdfd8db28f0b05609386bcb694fe1
|
3 |
+
size 998296048
|
model-00005-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d11f8561ebf65235a6efa3d53937c34b8e19d40c39652f6027ccd67f0ca6ea93
|
3 |
+
size 981502432
|
model-00006-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6118c8f2186119e1b3748e089746997172b6ded0269622d2d160fcc8b0466830
|
3 |
+
size 922798672
|
model-00007-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d40c4d375b9144269d1c980dc3b140cc80522f73d7bfc9bc4d58f16c4c04d3
|
3 |
+
size 989890712
|
model-00008-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:935cd5bb1c7c2bd8b5dbe945040e5bf4e9af22311ea2d6d8a9f2838c495242de
|
3 |
+
size 989890712
|
model-00009-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc72c8d262c6c29c4de44bd6a70e210d7cbd2e48bb7d1a5fd2575c38319dbb3
|
3 |
+
size 989890712
|
model-00010-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97bba49c468b87a065c9b70d9987237f4d22a69d97e66f2f85eac16103a6e427
|
3 |
+
size 989890712
|
model-00011-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cabafe03d0bcc02b7e66eae7cf73294e935d481a06be120569edb918d21303ce
|
3 |
+
size 956353224
|
model-00012-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75e3f6ea7be0693c9bc053f341cf0d26a75d11c6e126385ca101f17cc9fccc80
|
3 |
+
size 989890712
|
model-00013-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9905ab9b7fd022a538d63c3b8d4a128dc2f8e35b02999911cc4644331c6f3c0
|
3 |
+
size 989890712
|
model-00014-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59a24a0cc3d2dfe40877ff025595b5d33c2aa8c5f3b02cddde7b52b636bdd229
|
3 |
+
size 989890712
|
model-00015-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48480d42fe5dc2611d243ddcc6bcde0008cfa8c8d70b6fbc0532979ee1721fb3
|
3 |
+
size 989890704
|
model-00016-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a49a7ebb43a95cf77836743effcec9aef7cda2563485d2c18db74fe4114c627
|
3 |
+
size 998296048
|
model-00017-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df1bd9b883d2e4aea0f95f9e8198616a35977298357c824bb46637c03582f12e
|
3 |
+
size 989891160
|
model-00018-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e849008d89a0f55a797f8cfdb0e587ca12727e38bd26edab77952179186a55f6
|
3 |
+
size 914401640
|
model-00019-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a2e558ca0511ef3c9c879c48c38ddc14ab02266facea1fe36b1f16d897e3c15
|
3 |
+
size 989890704
|
model-00020-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55b92e7c6c1337438d9d98cb6f0d626d947b2749890f4df16f0385922b292ddf
|
3 |
+
size 989890688
|
model-00021-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98fe39fbe60e9d89ee09af937f8c0402928fd5d50af1bdec4f5200f6ffb33a4a
|
3 |
+
size 998287720
|
model-00022-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5acb632e18778e9bbba22293772756f5753bbae1d7349fb70679d547931186b1
|
3 |
+
size 947964480
|
model-00023-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ecaff86986e33c5888577ba41761990e9139d148623040597e01c8a6e7978ab
|
3 |
+
size 872441752
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 22335496192}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00001-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"unk_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": false
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": false
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": null,
|
41 |
+
"padding_side": "left",
|
42 |
+
"sp_model_kwargs": {},
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"split_special_tokens": false,
|
45 |
+
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": true
|
48 |
+
}
|